whisper-timestamped / tests /expected /naive /accurate_apollo11.mp3.words.json
acharyasagar's picture
Upload folder using huggingface_hub
89c4248 verified
{
"text": " Apollo 11, Houston, we got a recommendation for you on your Soyuz-EA GLEM-E-G-E-A. All right. Okay. Yeah, sir. Yeah, sir. Let's take that camera. Let's say it makes it want to go on the helmet we were going to have in B-1. The other one. And you can put the other one on the mic helmet. We'll show it to you in a quick screen. Over. All right. Yeah, sir. All right. Yeah, sir. There's a better helmet than B-1. That's the other one. Nice. Let's go in there. At least we're safe. We've got them in there. Helmet bags. And, uh, I guess we have helmets in the helmet bag. At least it's in the helmet bag. Right here. Right here. Yeah, we're taking it next day. Yeah, we're taking it next day. Yeah, it's a little bit of a delay on it. Yeah, you know what. We're gonna hack me on it. We're gonna hack you on it. We're gonna hack you on it. We're gonna hack you on it. With a cover, I tried it already. Okay, fine. We weren't sure of that, uh, just the suggestion. We thought we'd, uh, say you could check it out. It's not much of a hard to turn on, so, uh, I guess, uh, we're gonna come up with it. Let us know. Okay, no problem. Okay, no problem. We're gonna let you know when the end of... None. I'm glad you came. Everything's OK. Everything's OK. Yeah. You're safe.",
"segments": [
{
"id": 0,
"seek": 0,
"start": 0.54,
"end": 6.66,
"text": " Apollo 11, Houston, we got a recommendation for you on your Soyuz-EA GLEM-E-G-E-A.",
"tokens": [
50364,
25187,
2975,
11,
18717,
11,
321,
658,
257,
11879,
337,
291,
322,
428,
24758,
3334,
12,
36,
32,
460,
2634,
44,
12,
36,
12,
38,
12,
36,
12,
32,
13,
50714
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.578,
"words": [
{
"text": "Apollo",
"start": 0.54,
"end": 0.92,
"confidence": 0.425
},
{
"text": "11,",
"start": 0.92,
"end": 1.26,
"confidence": 0.842
},
{
"text": "Houston,",
"start": 1.52,
"end": 1.72,
"confidence": 0.665
},
{
"text": "we",
"start": 1.9,
"end": 1.94,
"confidence": 0.983
},
{
"text": "got",
"start": 1.94,
"end": 2.1,
"confidence": 0.743
},
{
"text": "a",
"start": 2.1,
"end": 2.26,
"confidence": 0.993
},
{
"text": "recommendation",
"start": 2.26,
"end": 2.86,
"confidence": 0.977
},
{
"text": "for",
"start": 2.86,
"end": 3.44,
"confidence": 0.94
},
{
"text": "you",
"start": 3.44,
"end": 3.6,
"confidence": 0.993
},
{
"text": "on",
"start": 3.6,
"end": 3.74,
"confidence": 0.918
},
{
"text": "your",
"start": 3.74,
"end": 3.94,
"confidence": 0.976
},
{
"text": "Soyuz-EA",
"start": 3.94,
"end": 5.26,
"confidence": 0.455
},
{
"text": "GLEM-E-G-E-A.",
"start": 5.26,
"end": 6.66,
"confidence": 0.436
}
]
},
{
"id": 1,
"seek": 0,
"start": 10.8,
"end": 11.08,
"text": " All right.",
"tokens": [
50714,
1057,
558,
13,
50914
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.14,
"words": [
{
"text": "All",
"start": 10.8,
"end": 10.82,
"confidence": 0.005
},
{
"text": "right.",
"start": 10.82,
"end": 11.08,
"confidence": 0.747
}
]
},
{
"id": 2,
"seek": 0,
"start": 12.2,
"end": 12.22,
"text": " Okay.",
"tokens": [
50914,
1033,
13,
50964
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.287,
"words": [
{
"text": "Okay.",
"start": 12.2,
"end": 12.22,
"confidence": 0.287
}
]
},
{
"id": 3,
"seek": 0,
"start": 12.22,
"end": 13.38,
"text": " Yeah, sir.",
"tokens": [
50964,
865,
11,
4735,
13,
51014
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.124,
"words": [
{
"text": "Yeah,",
"start": 12.22,
"end": 12.64,
"confidence": 0.113
},
{
"text": "sir.",
"start": 12.76,
"end": 13.38,
"confidence": 0.137
}
]
},
{
"id": 4,
"seek": 0,
"start": 13.38,
"end": 13.92,
"text": " Yeah, sir.",
"tokens": [
51014,
865,
11,
4735,
13,
51064
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.048,
"words": [
{
"text": "Yeah,",
"start": 13.38,
"end": 13.5,
"confidence": 0.089
},
{
"text": "sir.",
"start": 13.64,
"end": 13.92,
"confidence": 0.026
}
]
},
{
"id": 5,
"seek": 0,
"start": 13.92,
"end": 14.52,
"text": " Let's take that camera.",
"tokens": [
51064,
961,
311,
747,
300,
2799,
13,
51114
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.054,
"words": [
{
"text": "Let's",
"start": 13.92,
"end": 14.04,
"confidence": 0.035
},
{
"text": "take",
"start": 14.04,
"end": 14.14,
"confidence": 0.027
},
{
"text": "that",
"start": 14.14,
"end": 14.22,
"confidence": 0.037
},
{
"text": "camera.",
"start": 14.22,
"end": 14.52,
"confidence": 0.14
}
]
},
{
"id": 6,
"seek": 0,
"start": 14.52,
"end": 19.08,
"text": " Let's say it makes it want to go on the helmet we were going to have in B-1.",
"tokens": [
51114,
961,
311,
584,
309,
1669,
309,
528,
281,
352,
322,
264,
15922,
321,
645,
516,
281,
362,
294,
363,
12,
16,
13,
51314
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.29,
"words": [
{
"text": "Let's",
"start": 14.52,
"end": 14.82,
"confidence": 0.124
},
{
"text": "say",
"start": 14.82,
"end": 14.98,
"confidence": 0.29
},
{
"text": "it",
"start": 14.98,
"end": 15.04,
"confidence": 0.029
},
{
"text": "makes",
"start": 15.04,
"end": 15.64,
"confidence": 0.633
},
{
"text": "it",
"start": 15.64,
"end": 15.86,
"confidence": 0.948
},
{
"text": "want",
"start": 15.86,
"end": 16.08,
"confidence": 0.249
},
{
"text": "to",
"start": 16.08,
"end": 16.18,
"confidence": 0.969
},
{
"text": "go",
"start": 16.18,
"end": 16.38,
"confidence": 0.816
},
{
"text": "on",
"start": 16.38,
"end": 16.6,
"confidence": 0.934
},
{
"text": "the",
"start": 16.6,
"end": 16.76,
"confidence": 0.45
},
{
"text": "helmet",
"start": 16.76,
"end": 17.24,
"confidence": 0.003
},
{
"text": "we",
"start": 17.24,
"end": 17.54,
"confidence": 0.019
},
{
"text": "were",
"start": 17.54,
"end": 17.78,
"confidence": 0.181
},
{
"text": "going",
"start": 17.78,
"end": 17.96,
"confidence": 0.637
},
{
"text": "to",
"start": 17.96,
"end": 18.12,
"confidence": 0.965
},
{
"text": "have",
"start": 18.12,
"end": 18.18,
"confidence": 0.967
},
{
"text": "in",
"start": 18.18,
"end": 18.36,
"confidence": 0.902
},
{
"text": "B-1.",
"start": 18.36,
"end": 19.08,
"confidence": 0.471
}
]
},
{
"id": 7,
"seek": 0,
"start": 19.08,
"end": 19.84,
"text": " The other one.",
"tokens": [
51314,
440,
661,
472,
13,
51364
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.126,
"words": [
{
"text": "The",
"start": 19.08,
"end": 19.38,
"confidence": 0.004
},
{
"text": "other",
"start": 19.38,
"end": 19.62,
"confidence": 0.141
},
{
"text": "one.",
"start": 19.62,
"end": 19.84,
"confidence": 0.691
}
]
},
{
"id": 8,
"seek": 0,
"start": 20.04,
"end": 22.8,
"text": " And you can put the other one on the mic helmet.",
"tokens": [
51364,
400,
291,
393,
829,
264,
661,
472,
322,
264,
3123,
15922,
13,
51514
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.405,
"words": [
{
"text": "And",
"start": 20.04,
"end": 20.22,
"confidence": 0.344
},
{
"text": "you",
"start": 20.22,
"end": 20.32,
"confidence": 0.892
},
{
"text": "can",
"start": 20.32,
"end": 20.48,
"confidence": 0.126
},
{
"text": "put",
"start": 20.48,
"end": 20.64,
"confidence": 0.894
},
{
"text": "the",
"start": 20.64,
"end": 20.84,
"confidence": 0.979
},
{
"text": "other",
"start": 20.84,
"end": 21.0,
"confidence": 0.996
},
{
"text": "one",
"start": 21.0,
"end": 21.18,
"confidence": 0.972
},
{
"text": "on",
"start": 21.18,
"end": 21.38,
"confidence": 0.969
},
{
"text": "the",
"start": 21.38,
"end": 21.66,
"confidence": 0.09
},
{
"text": "mic",
"start": 21.66,
"end": 22.48,
"confidence": 0.616
},
{
"text": "helmet.",
"start": 22.48,
"end": 22.8,
"confidence": 0.105
}
]
},
{
"id": 9,
"seek": 0,
"start": 22.8,
"end": 24.36,
"text": " We'll show it to you in a quick screen.",
"tokens": [
51514,
492,
603,
855,
309,
281,
291,
294,
257,
1702,
2568,
13,
51614
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.121,
"words": [
{
"text": "We'll",
"start": 22.8,
"end": 23.0,
"confidence": 0.08
},
{
"text": "show",
"start": 23.0,
"end": 23.24,
"confidence": 0.013
},
{
"text": "it",
"start": 23.24,
"end": 23.36,
"confidence": 0.12
},
{
"text": "to",
"start": 23.36,
"end": 23.52,
"confidence": 0.356
},
{
"text": "you",
"start": 23.52,
"end": 23.64,
"confidence": 0.609
},
{
"text": "in",
"start": 23.64,
"end": 23.86,
"confidence": 0.287
},
{
"text": "a",
"start": 23.86,
"end": 23.88,
"confidence": 0.723
},
{
"text": "quick",
"start": 23.88,
"end": 24.04,
"confidence": 0.016
},
{
"text": "screen.",
"start": 24.04,
"end": 24.36,
"confidence": 0.109
}
]
},
{
"id": 10,
"seek": 0,
"start": 24.84,
"end": 25.1,
"text": " Over.",
"tokens": [
51614,
4886,
13,
51664
],
"temperature": 0.0,
"avg_logprob": -0.5322377604822959,
"compression_ratio": 1.4690265486725664,
"no_speech_prob": 0.44994914531707764,
"confidence": 0.062,
"words": [
{
"text": "Over.",
"start": 24.84,
"end": 25.1,
"confidence": 0.062
}
]
},
{
"id": 11,
"seek": 2600,
"start": 31.32,
"end": 31.36,
"text": " All right.",
"tokens": [
50364,
1057,
558,
13,
50614
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.108,
"words": [
{
"text": "All",
"start": 31.32,
"end": 31.34,
"confidence": 0.003
},
{
"text": "right.",
"start": 31.34,
"end": 31.36,
"confidence": 0.677
}
]
},
{
"id": 12,
"seek": 2600,
"start": 31.36,
"end": 32.06,
"text": " Yeah, sir.",
"tokens": [
50614,
865,
11,
4735,
13,
50664
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.035,
"words": [
{
"text": "Yeah,",
"start": 31.36,
"end": 31.56,
"confidence": 0.033
},
{
"text": "sir.",
"start": 31.56,
"end": 32.06,
"confidence": 0.036
}
]
},
{
"id": 13,
"seek": 2600,
"start": 32.26,
"end": 33.0,
"text": " All right.",
"tokens": [
50664,
1057,
558,
13,
50714
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.201,
"words": [
{
"text": "All",
"start": 32.26,
"end": 32.86,
"confidence": 0.022
},
{
"text": "right.",
"start": 32.86,
"end": 33.0,
"confidence": 0.607
}
]
},
{
"id": 14,
"seek": 2600,
"start": 33.0,
"end": 33.5,
"text": " Yeah, sir.",
"tokens": [
50714,
865,
11,
4735,
13,
50764
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.044,
"words": [
{
"text": "Yeah,",
"start": 33.0,
"end": 33.16,
"confidence": 0.208
},
{
"text": "sir.",
"start": 33.22,
"end": 33.5,
"confidence": 0.009
}
]
},
{
"id": 15,
"seek": 2600,
"start": 33.5,
"end": 34.98,
"text": " There's a better helmet than B-1.",
"tokens": [
50764,
821,
311,
257,
1101,
15922,
813,
363,
12,
16,
13,
50814
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.04,
"words": [
{
"text": "There's",
"start": 33.5,
"end": 33.9,
"confidence": 0.022
},
{
"text": "a",
"start": 33.9,
"end": 33.92,
"confidence": 0.264
},
{
"text": "better",
"start": 33.92,
"end": 33.94,
"confidence": 0.228
},
{
"text": "helmet",
"start": 33.94,
"end": 34.2,
"confidence": 0.004
},
{
"text": "than",
"start": 34.2,
"end": 34.6,
"confidence": 0.352
},
{
"text": "B-1.",
"start": 34.6,
"end": 34.98,
"confidence": 0.022
}
]
},
{
"id": 16,
"seek": 2600,
"start": 35.0,
"end": 35.8,
"text": " That's the other one.",
"tokens": [
50814,
663,
311,
264,
661,
472,
13,
50864
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.277,
"words": [
{
"text": "That's",
"start": 35.0,
"end": 35.38,
"confidence": 0.161
},
{
"text": "the",
"start": 35.38,
"end": 35.48,
"confidence": 0.515
},
{
"text": "other",
"start": 35.48,
"end": 35.6,
"confidence": 0.965
},
{
"text": "one.",
"start": 35.6,
"end": 35.8,
"confidence": 0.188
}
]
},
{
"id": 17,
"seek": 2600,
"start": 35.8,
"end": 36.04,
"text": " Nice.",
"tokens": [
50864,
5490,
13,
50914
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.011,
"words": [
{
"text": "Nice.",
"start": 35.8,
"end": 36.04,
"confidence": 0.011
}
]
},
{
"id": 18,
"seek": 2600,
"start": 37.62,
"end": 38.38,
"text": " Let's go in there.",
"tokens": [
50914,
961,
311,
352,
294,
456,
13,
50964
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.125,
"words": [
{
"text": "Let's",
"start": 37.62,
"end": 38.1,
"confidence": 0.022
},
{
"text": "go",
"start": 38.1,
"end": 38.12,
"confidence": 0.626
},
{
"text": "in",
"start": 38.12,
"end": 38.26,
"confidence": 0.037
},
{
"text": "there.",
"start": 38.26,
"end": 38.38,
"confidence": 0.579
}
]
},
{
"id": 19,
"seek": 2600,
"start": 38.38,
"end": 39.2,
"text": " At least we're safe.",
"tokens": [
50964,
1711,
1935,
321,
434,
3273,
13,
51014
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.107,
"words": [
{
"text": "At",
"start": 38.38,
"end": 38.44,
"confidence": 0.003
},
{
"text": "least",
"start": 38.44,
"end": 38.72,
"confidence": 0.125
},
{
"text": "we're",
"start": 38.72,
"end": 38.98,
"confidence": 0.091
},
{
"text": "safe.",
"start": 38.98,
"end": 39.2,
"confidence": 0.715
}
]
},
{
"id": 20,
"seek": 2600,
"start": 39.88,
"end": 40.54,
"text": " We've got them in there.",
"tokens": [
51014,
492,
600,
658,
552,
294,
456,
13,
51064
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.077,
"words": [
{
"text": "We've",
"start": 39.88,
"end": 40.36,
"confidence": 0.055
},
{
"text": "got",
"start": 40.36,
"end": 40.48,
"confidence": 0.749
},
{
"text": "them",
"start": 40.48,
"end": 40.5,
"confidence": 0.003
},
{
"text": "in",
"start": 40.5,
"end": 40.52,
"confidence": 0.053
},
{
"text": "there.",
"start": 40.52,
"end": 40.54,
"confidence": 0.211
}
]
},
{
"id": 21,
"seek": 2600,
"start": 40.54,
"end": 41.04,
"text": " Helmet bags.",
"tokens": [
51064,
6128,
5537,
10405,
13,
51114
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.001,
"words": [
{
"text": "Helmet",
"start": 40.54,
"end": 40.66,
"confidence": 0.001
},
{
"text": "bags.",
"start": 40.66,
"end": 41.04,
"confidence": 0.002
}
]
},
{
"id": 22,
"seek": 2600,
"start": 43.18,
"end": 47.4,
"text": " And, uh, I guess we have helmets in the helmet bag.",
"tokens": [
51114,
400,
11,
2232,
11,
286,
2041,
321,
362,
42022,
294,
264,
15922,
3411,
13,
51464
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.175,
"words": [
{
"text": "And,",
"start": 43.18,
"end": 43.2,
"confidence": 0.052
},
{
"text": "uh,",
"start": 43.48,
"end": 43.74,
"confidence": 0.745
},
{
"text": "I",
"start": 43.86,
"end": 44.04,
"confidence": 0.341
},
{
"text": "guess",
"start": 44.04,
"end": 44.2,
"confidence": 0.283
},
{
"text": "we",
"start": 44.2,
"end": 44.52,
"confidence": 0.055
},
{
"text": "have",
"start": 44.52,
"end": 45.48,
"confidence": 0.053
},
{
"text": "helmets",
"start": 45.48,
"end": 46.5,
"confidence": 0.005
},
{
"text": "in",
"start": 46.5,
"end": 46.72,
"confidence": 0.216
},
{
"text": "the",
"start": 46.72,
"end": 46.92,
"confidence": 0.619
},
{
"text": "helmet",
"start": 46.92,
"end": 47.08,
"confidence": 0.831
},
{
"text": "bag.",
"start": 47.08,
"end": 47.4,
"confidence": 0.329
}
]
},
{
"id": 23,
"seek": 2600,
"start": 48.2,
"end": 49.52,
"text": " At least it's in the helmet bag.",
"tokens": [
51464,
1711,
1935,
309,
311,
294,
264,
15922,
3411,
13,
51564
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.122,
"words": [
{
"text": "At",
"start": 48.2,
"end": 48.34,
"confidence": 0.096
},
{
"text": "least",
"start": 48.34,
"end": 48.6,
"confidence": 0.761
},
{
"text": "it's",
"start": 48.6,
"end": 48.86,
"confidence": 0.339
},
{
"text": "in",
"start": 48.86,
"end": 48.96,
"confidence": 0.151
},
{
"text": "the",
"start": 48.96,
"end": 49.1,
"confidence": 0.223
},
{
"text": "helmet",
"start": 49.1,
"end": 49.18,
"confidence": 0.006
},
{
"text": "bag.",
"start": 49.18,
"end": 49.52,
"confidence": 0.06
}
]
},
{
"id": 24,
"seek": 2600,
"start": 49.52,
"end": 50.38,
"text": " Right here.",
"tokens": [
51564,
1779,
510,
13,
51614
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.059,
"words": [
{
"text": "Right",
"start": 49.52,
"end": 49.62,
"confidence": 0.027
},
{
"text": "here.",
"start": 49.62,
"end": 50.38,
"confidence": 0.088
}
]
},
{
"id": 25,
"seek": 2600,
"start": 51.52,
"end": 51.98,
"text": " Right here.",
"tokens": [
51614,
1779,
510,
13,
51664
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.017,
"words": [
{
"text": "Right",
"start": 51.52,
"end": 51.72,
"confidence": 0.001
},
{
"text": "here.",
"start": 51.72,
"end": 51.98,
"confidence": 0.067
}
]
},
{
"id": 26,
"seek": 2600,
"start": 51.98,
"end": 52.74,
"text": " Yeah, we're taking it next day.",
"tokens": [
51664,
865,
11,
321,
434,
1940,
309,
958,
786,
13,
51714
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.047,
"words": [
{
"text": "Yeah,",
"start": 51.98,
"end": 52.28,
"confidence": 0.043
},
{
"text": "we're",
"start": 52.28,
"end": 52.3,
"confidence": 0.288
},
{
"text": "taking",
"start": 52.3,
"end": 52.32,
"confidence": 0.005
},
{
"text": "it",
"start": 52.32,
"end": 52.34,
"confidence": 0.052
},
{
"text": "next",
"start": 52.34,
"end": 52.52,
"confidence": 0.002
},
{
"text": "day.",
"start": 52.52,
"end": 52.74,
"confidence": 0.113
}
]
},
{
"id": 27,
"seek": 2600,
"start": 52.74,
"end": 54.1,
"text": " Yeah, we're taking it next day.",
"tokens": [
51714,
865,
11,
321,
434,
1940,
309,
958,
786,
13,
51764
],
"temperature": 0.0,
"avg_logprob": -0.5041401628134907,
"compression_ratio": 1.9243243243243244,
"no_speech_prob": 0.08131657540798187,
"confidence": 0.41,
"words": [
{
"text": "Yeah,",
"start": 52.74,
"end": 53.24,
"confidence": 0.601
},
{
"text": "we're",
"start": 53.34,
"end": 53.44,
"confidence": 0.703
},
{
"text": "taking",
"start": 53.44,
"end": 53.62,
"confidence": 0.261
},
{
"text": "it",
"start": 53.62,
"end": 53.76,
"confidence": 0.247
},
{
"text": "next",
"start": 53.76,
"end": 53.88,
"confidence": 0.404
},
{
"text": "day.",
"start": 53.88,
"end": 54.1,
"confidence": 0.266
}
]
},
{
"id": 28,
"seek": 5400,
"start": 54.1,
"end": 55.58,
"text": " Yeah, it's a little bit of a delay on it.",
"tokens": [
50364,
865,
11,
309,
311,
257,
707,
857,
295,
257,
8577,
322,
309,
13,
50414
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.076,
"words": [
{
"text": "Yeah,",
"start": 54.1,
"end": 54.16,
"confidence": 0.089
},
{
"text": "it's",
"start": 54.24,
"end": 54.48,
"confidence": 0.085
},
{
"text": "a",
"start": 54.48,
"end": 54.56,
"confidence": 0.33
},
{
"text": "little",
"start": 54.56,
"end": 55.16,
"confidence": 0.003
},
{
"text": "bit",
"start": 55.16,
"end": 55.48,
"confidence": 0.367
},
{
"text": "of",
"start": 55.48,
"end": 55.5,
"confidence": 0.176
},
{
"text": "a",
"start": 55.5,
"end": 55.52,
"confidence": 0.67
},
{
"text": "delay",
"start": 55.52,
"end": 55.54,
"confidence": 0.006
},
{
"text": "on",
"start": 55.54,
"end": 55.56,
"confidence": 0.019
},
{
"text": "it.",
"start": 55.56,
"end": 55.58,
"confidence": 0.098
}
]
},
{
"id": 29,
"seek": 5400,
"start": 55.58,
"end": 56.28,
"text": " Yeah, you know what.",
"tokens": [
50414,
865,
11,
291,
458,
437,
13,
50464
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.051,
"words": [
{
"text": "Yeah,",
"start": 55.58,
"end": 55.6,
"confidence": 0.023
},
{
"text": "you",
"start": 56.0,
"end": 56.02,
"confidence": 0.034
},
{
"text": "know",
"start": 56.02,
"end": 56.2,
"confidence": 0.074
},
{
"text": "what.",
"start": 56.2,
"end": 56.28,
"confidence": 0.116
}
]
},
{
"id": 30,
"seek": 5400,
"start": 56.46,
"end": 57.52,
"text": " We're gonna hack me on it.",
"tokens": [
50464,
492,
434,
799,
10339,
385,
322,
309,
13,
50514
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.017,
"words": [
{
"text": "We're",
"start": 56.46,
"end": 56.9,
"confidence": 0.106
},
{
"text": "gonna",
"start": 56.9,
"end": 57.16,
"confidence": 0.031
},
{
"text": "hack",
"start": 57.16,
"end": 57.4,
"confidence": 0.003
},
{
"text": "me",
"start": 57.4,
"end": 57.48,
"confidence": 0.0
},
{
"text": "on",
"start": 57.48,
"end": 57.5,
"confidence": 0.002
},
{
"text": "it.",
"start": 57.5,
"end": 57.52,
"confidence": 0.075
}
]
},
{
"id": 31,
"seek": 5400,
"start": 57.52,
"end": 58.5,
"text": " We're gonna hack you on it.",
"tokens": [
50514,
492,
434,
799,
10339,
291,
322,
309,
13,
50564
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.023,
"words": [
{
"text": "We're",
"start": 57.52,
"end": 58.16,
"confidence": 0.069
},
{
"text": "gonna",
"start": 58.16,
"end": 58.3,
"confidence": 0.027
},
{
"text": "hack",
"start": 58.3,
"end": 58.34,
"confidence": 0.0
},
{
"text": "you",
"start": 58.34,
"end": 58.46,
"confidence": 0.139
},
{
"text": "on",
"start": 58.46,
"end": 58.48,
"confidence": 0.021
},
{
"text": "it.",
"start": 58.48,
"end": 58.5,
"confidence": 0.112
}
]
},
{
"id": 32,
"seek": 5400,
"start": 58.5,
"end": 59.4,
"text": " We're gonna hack you on it.",
"tokens": [
50564,
492,
434,
799,
10339,
291,
322,
309,
13,
50614
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.039,
"words": [
{
"text": "We're",
"start": 58.5,
"end": 58.62,
"confidence": 0.052
},
{
"text": "gonna",
"start": 58.62,
"end": 58.74,
"confidence": 0.037
},
{
"text": "hack",
"start": 58.74,
"end": 58.76,
"confidence": 0.0
},
{
"text": "you",
"start": 58.76,
"end": 58.94,
"confidence": 0.602
},
{
"text": "on",
"start": 58.94,
"end": 59.16,
"confidence": 0.227
},
{
"text": "it.",
"start": 59.16,
"end": 59.4,
"confidence": 0.105
}
]
},
{
"id": 33,
"seek": 5400,
"start": 59.4,
"end": 60.04,
"text": " We're gonna hack you on it.",
"tokens": [
50614,
492,
434,
799,
10339,
291,
322,
309,
13,
50664
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.023,
"words": [
{
"text": "We're",
"start": 59.4,
"end": 59.58,
"confidence": 0.047
},
{
"text": "gonna",
"start": 59.58,
"end": 59.6,
"confidence": 0.113
},
{
"text": "hack",
"start": 59.6,
"end": 59.7,
"confidence": 0.0
},
{
"text": "you",
"start": 59.7,
"end": 59.9,
"confidence": 0.091
},
{
"text": "on",
"start": 59.9,
"end": 59.94,
"confidence": 0.008
},
{
"text": "it.",
"start": 59.94,
"end": 60.04,
"confidence": 0.099
}
]
},
{
"id": 34,
"seek": 5400,
"start": 60.04,
"end": 61.82,
"text": " With a cover, I tried it already.",
"tokens": [
50664,
2022,
257,
2060,
11,
286,
3031,
309,
1217,
13,
50764
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.189,
"words": [
{
"text": "With",
"start": 60.04,
"end": 60.16,
"confidence": 0.071
},
{
"text": "a",
"start": 60.16,
"end": 60.8,
"confidence": 0.572
},
{
"text": "cover,",
"start": 60.8,
"end": 61.02,
"confidence": 0.064
},
{
"text": "I",
"start": 61.16,
"end": 61.28,
"confidence": 0.884
},
{
"text": "tried",
"start": 61.28,
"end": 61.44,
"confidence": 0.009
},
{
"text": "it",
"start": 61.44,
"end": 61.64,
"confidence": 0.364
},
{
"text": "already.",
"start": 61.64,
"end": 61.82,
"confidence": 0.8
}
]
},
{
"id": 35,
"seek": 5400,
"start": 62.52,
"end": 63.06,
"text": " Okay, fine.",
"tokens": [
50764,
1033,
11,
2489,
13,
50814
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.473,
"words": [
{
"text": "Okay,",
"start": 62.52,
"end": 62.76,
"confidence": 0.383
},
{
"text": "fine.",
"start": 62.88,
"end": 63.06,
"confidence": 0.584
}
]
},
{
"id": 36,
"seek": 5400,
"start": 63.06,
"end": 65.12,
"text": " We weren't sure of that, uh, just the suggestion.",
"tokens": [
50814,
492,
4999,
380,
988,
295,
300,
11,
2232,
11,
445,
264,
16541,
13,
50914
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.478,
"words": [
{
"text": "We",
"start": 63.06,
"end": 63.26,
"confidence": 0.274
},
{
"text": "weren't",
"start": 63.26,
"end": 63.58,
"confidence": 0.918
},
{
"text": "sure",
"start": 63.58,
"end": 63.72,
"confidence": 0.976
},
{
"text": "of",
"start": 63.72,
"end": 63.86,
"confidence": 0.438
},
{
"text": "that,",
"start": 63.86,
"end": 64.0,
"confidence": 0.58
},
{
"text": "uh,",
"start": 64.14,
"end": 64.3,
"confidence": 0.318
},
{
"text": "just",
"start": 64.34,
"end": 64.58,
"confidence": 0.401
},
{
"text": "the",
"start": 64.58,
"end": 64.78,
"confidence": 0.6
},
{
"text": "suggestion.",
"start": 64.78,
"end": 65.12,
"confidence": 0.291
}
]
},
{
"id": 37,
"seek": 5400,
"start": 65.12,
"end": 67.7,
"text": " We thought we'd, uh, say you could check it out.",
"tokens": [
50914,
492,
1194,
321,
1116,
11,
2232,
11,
584,
291,
727,
1520,
309,
484,
13,
51064
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.532,
"words": [
{
"text": "We",
"start": 65.12,
"end": 65.32,
"confidence": 0.134
},
{
"text": "thought",
"start": 65.32,
"end": 65.56,
"confidence": 0.834
},
{
"text": "we'd,",
"start": 65.56,
"end": 65.9,
"confidence": 0.38
},
{
"text": "uh,",
"start": 65.96,
"end": 66.02,
"confidence": 0.663
},
{
"text": "say",
"start": 66.76,
"end": 66.94,
"confidence": 0.176
},
{
"text": "you",
"start": 66.94,
"end": 67.08,
"confidence": 0.828
},
{
"text": "could",
"start": 67.08,
"end": 67.22,
"confidence": 0.7
},
{
"text": "check",
"start": 67.22,
"end": 67.38,
"confidence": 0.65
},
{
"text": "it",
"start": 67.38,
"end": 67.56,
"confidence": 0.979
},
{
"text": "out.",
"start": 67.56,
"end": 67.7,
"confidence": 0.91
}
]
},
{
"id": 38,
"seek": 5400,
"start": 68.14,
"end": 71.9,
"text": " It's not much of a hard to turn on, so, uh, I guess, uh, we're gonna come up with it.",
"tokens": [
51064,
467,
311,
406,
709,
295,
257,
1152,
281,
1261,
322,
11,
370,
11,
2232,
11,
286,
2041,
11,
2232,
11,
321,
434,
799,
808,
493,
365,
309,
13,
51264
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.306,
"words": [
{
"text": "It's",
"start": 68.14,
"end": 68.3,
"confidence": 0.098
},
{
"text": "not",
"start": 68.3,
"end": 68.4,
"confidence": 0.375
},
{
"text": "much",
"start": 68.4,
"end": 68.58,
"confidence": 0.863
},
{
"text": "of",
"start": 68.58,
"end": 68.72,
"confidence": 0.227
},
{
"text": "a",
"start": 68.72,
"end": 68.86,
"confidence": 0.339
},
{
"text": "hard",
"start": 68.86,
"end": 68.88,
"confidence": 0.014
},
{
"text": "to",
"start": 68.88,
"end": 68.98,
"confidence": 0.073
},
{
"text": "turn",
"start": 68.98,
"end": 69.1,
"confidence": 0.767
},
{
"text": "on,",
"start": 69.1,
"end": 69.24,
"confidence": 0.101
},
{
"text": "so,",
"start": 69.44,
"end": 69.58,
"confidence": 0.389
},
{
"text": "uh,",
"start": 69.7,
"end": 69.84,
"confidence": 0.5
},
{
"text": "I",
"start": 70.3,
"end": 70.5,
"confidence": 0.72
},
{
"text": "guess,",
"start": 70.5,
"end": 70.66,
"confidence": 0.731
},
{
"text": "uh,",
"start": 70.74,
"end": 70.9,
"confidence": 0.969
},
{
"text": "we're",
"start": 70.92,
"end": 71.1,
"confidence": 0.614
},
{
"text": "gonna",
"start": 71.1,
"end": 71.24,
"confidence": 0.481
},
{
"text": "come",
"start": 71.24,
"end": 71.42,
"confidence": 0.84
},
{
"text": "up",
"start": 71.42,
"end": 71.6,
"confidence": 0.84
},
{
"text": "with",
"start": 71.6,
"end": 71.76,
"confidence": 0.407
},
{
"text": "it.",
"start": 71.76,
"end": 71.9,
"confidence": 0.054
}
]
},
{
"id": 39,
"seek": 5400,
"start": 71.9,
"end": 72.46,
"text": " Let us know.",
"tokens": [
51264,
961,
505,
458,
13,
51314
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.313,
"words": [
{
"text": "Let",
"start": 71.9,
"end": 72.08,
"confidence": 0.035
},
{
"text": "us",
"start": 72.08,
"end": 72.24,
"confidence": 0.466
},
{
"text": "know.",
"start": 72.24,
"end": 72.46,
"confidence": 0.772
}
]
},
{
"id": 40,
"seek": 5400,
"start": 72.5,
"end": 72.7,
"text": " Okay, no problem.",
"tokens": [
51314,
1033,
11,
572,
1154,
13,
51364
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.04,
"words": [
{
"text": "Okay,",
"start": 72.5,
"end": 72.52,
"confidence": 0.02
},
{
"text": "no",
"start": 72.52,
"end": 72.56,
"confidence": 0.003
},
{
"text": "problem.",
"start": 72.56,
"end": 72.7,
"confidence": 0.299
}
]
},
{
"id": 41,
"seek": 5400,
"start": 73.68,
"end": 75.2,
"text": " Okay, no problem.",
"tokens": [
51364,
1033,
11,
572,
1154,
13,
51414
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.175,
"words": [
{
"text": "Okay,",
"start": 73.68,
"end": 74.48,
"confidence": 0.044
},
{
"text": "no",
"start": 74.64,
"end": 74.86,
"confidence": 0.126
},
{
"text": "problem.",
"start": 74.86,
"end": 75.2,
"confidence": 0.813
}
]
},
{
"id": 42,
"seek": 5400,
"start": 76.74,
"end": 77.48,
"text": " We're gonna let you know when the end of...",
"tokens": [
51414,
492,
434,
799,
718,
291,
458,
562,
264,
917,
295,
485,
51514
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.056,
"words": [
{
"text": "We're",
"start": 76.74,
"end": 76.82,
"confidence": 0.04
},
{
"text": "gonna",
"start": 76.82,
"end": 76.84,
"confidence": 0.047
},
{
"text": "let",
"start": 76.84,
"end": 76.86,
"confidence": 0.01
},
{
"text": "you",
"start": 76.86,
"end": 77.14,
"confidence": 0.16
},
{
"text": "know",
"start": 77.14,
"end": 77.18,
"confidence": 0.642
},
{
"text": "when",
"start": 77.18,
"end": 77.34,
"confidence": 0.194
},
{
"text": "the",
"start": 77.34,
"end": 77.4,
"confidence": 0.053
},
{
"text": "end",
"start": 77.4,
"end": 77.46,
"confidence": 0.005
},
{
"text": "of...",
"start": 77.46,
"end": 77.48,
"confidence": 0.062
}
]
},
{
"id": 43,
"seek": 5400,
"start": 78.04,
"end": 78.22,
"text": " None.",
"tokens": [
51514,
14492,
13,
51564
],
"temperature": 0.6000000000000001,
"avg_logprob": -0.5010345458984375,
"compression_ratio": 1.9803149606299213,
"no_speech_prob": 0.2010815143585205,
"confidence": 0.02,
"words": [
{
"text": "None.",
"start": 78.04,
"end": 78.22,
"confidence": 0.02
}
]
},
{
"id": 44,
"seek": 7800,
"start": 78.22,
"end": 78.76,
"text": " I'm glad you came.",
"tokens": [
50364,
286,
478,
5404,
291,
1361,
13,
50589
],
"temperature": 1.0,
"avg_logprob": -1.8937584661668347,
"compression_ratio": 1.1833333333333333,
"no_speech_prob": 0.2503969073295593,
"confidence": 0.072,
"words": [
{
"text": "I'm",
"start": 78.22,
"end": 78.26,
"confidence": 0.042
},
{
"text": "glad",
"start": 78.26,
"end": 78.28,
"confidence": 0.019
},
{
"text": "you",
"start": 78.28,
"end": 78.68,
"confidence": 0.196
},
{
"text": "came.",
"start": 78.68,
"end": 78.76,
"confidence": 0.147
}
]
},
{
"id": 45,
"seek": 7800,
"start": 84.96,
"end": 85.88,
"text": " Everything's OK.",
"tokens": [
50724,
5471,
311,
2264,
13,
50774
],
"temperature": 1.0,
"avg_logprob": -1.8937584661668347,
"compression_ratio": 1.1833333333333333,
"no_speech_prob": 0.2503969073295593,
"confidence": 0.028,
"words": [
{
"text": "Everything's",
"start": 84.96,
"end": 85.86,
"confidence": 0.007
},
{
"text": "OK.",
"start": 85.86,
"end": 85.88,
"confidence": 0.118
}
]
},
{
"id": 46,
"seek": 7800,
"start": 86.5,
"end": 87.32,
"text": " Everything's OK.",
"tokens": [
50799,
5471,
311,
2264,
13,
50849
],
"temperature": 1.0,
"avg_logprob": -1.8937584661668347,
"compression_ratio": 1.1833333333333333,
"no_speech_prob": 0.2503969073295593,
"confidence": 0.048,
"words": [
{
"text": "Everything's",
"start": 86.5,
"end": 87.14,
"confidence": 0.015
},
{
"text": "OK.",
"start": 87.14,
"end": 87.32,
"confidence": 0.154
}
]
},
{
"id": 47,
"seek": 7800,
"start": 87.32,
"end": 87.58,
"text": " Yeah.",
"tokens": [
50849,
865,
13,
50899
],
"temperature": 1.0,
"avg_logprob": -1.8937584661668347,
"compression_ratio": 1.1833333333333333,
"no_speech_prob": 0.2503969073295593,
"confidence": 0.064,
"words": [
{
"text": "Yeah.",
"start": 87.32,
"end": 87.58,
"confidence": 0.064
}
]
},
{
"id": 48,
"seek": 7800,
"start": 88.2,
"end": 88.24,
"text": " You're safe.",
"tokens": [
50899,
509,
434,
3273,
13,
50949
],
"temperature": 1.0,
"avg_logprob": -1.8937584661668347,
"compression_ratio": 1.1833333333333333,
"no_speech_prob": 0.2503969073295593,
"confidence": 0.017,
"words": [
{
"text": "You're",
"start": 88.2,
"end": 88.22,
"confidence": 0.009
},
{
"text": "safe.",
"start": 88.22,
"end": 88.24,
"confidence": 0.03
}
]
}
],
"language": "en"
}